JP7809992B2 - Processing device, processing method, and program - Google Patents

Description

The present invention relates to a processing device, a processing method, and a program.

Patent Document 1 discloses technology for extracting companies similar to a company being evaluated based on correlation values in corporate attributes and correlation values in financial indicators. Corporate attributes include number of employees, percentage of foreign employees, gender ratio, target market, number of affiliated companies, size of subsidiary, nationality, type of business transaction, public nature, infrastructure nature, etc. Financial indicators include stability of stock price increase rate, stability of market capitalization increase rate, profit margin on sales, stability of ROE (return on equity), stability of ROIC (return on invested capital), stability of minimum free cash flow (FCF), etc.

WO 2013/179884

The objective of this invention is to provide technology for conducting corporate evaluations using a new, unprecedented method.

According to the present invention,
A processing device is provided that has a grouping means for grouping a plurality of reference objects based on financial indicators for a target period, technical indicators relating to changes in the financial indicators for the target period and prior to that period over time, and expert indicators generated by processing the financial indicators for the target period according to predetermined rules.

Further, according to the present invention,
The computer
A processing method is provided that executes a grouping step of grouping multiple reference targets based on financial indicators for a target period, technical indicators relating to changes in the financial indicators for the target period and prior to that period over time, and expert indicators generated by processing the financial indicators for the target period according to predetermined rules.

Further, according to the present invention,
Computer,
A program is provided that functions as a grouping means for grouping multiple reference targets based on financial indicators for a target period, technical indicators relating to changes in the financial indicators for the target period and prior to that period over time, and expert indicators generated by processing the financial indicators for the target period according to predetermined rules.

This invention realizes technology for conducting corporate evaluations using a new, unprecedented method.

FIG. 2 is a diagram illustrating an example of a hardware configuration of a processing device according to the present embodiment. FIG. 2 is a diagram illustrating an example of a functional block diagram of the processing apparatus according to the present embodiment. FIG. 2 is a diagram schematically illustrating an example of information processed by the processing device of the present embodiment. 10A and 10B are diagrams illustrating a grouping process performed by the processing device of the present embodiment. FIG. 2 is a diagram schematically illustrating an example of information processed by the processing device of the present embodiment. FIG. 2 is a diagram illustrating an example of a functional block diagram of the processing apparatus according to the present embodiment. FIG. 2 is a diagram schematically illustrating an example of information output by the processing device of the present embodiment. FIG. 2 is a diagram schematically illustrating an example of information output by the processing device of the present embodiment. 10 is a flowchart showing an example of a processing flow of the processing device of the present embodiment.

Embodiments of the present invention will be described below with reference to the drawings. Note that in all drawings, similar components will be designated by similar reference numerals, and descriptions will be omitted where appropriate.

First Embodiment
"overview"
The processing device of this embodiment treats data for one company for one fiscal year as one reference object, and groups multiple reference objects obtained from data for multiple companies for multiple fiscal years together based on similar content. In this grouping, the processing device of this embodiment uses financial indicators for the target fiscal year, technical indicators related to changes over time in financial indicators for the target fiscal year and earlier, and expert indicators generated by processing the financial indicators for the target fiscal year according to predetermined rules.

"Hardware Configuration"
Next, an example of the hardware configuration of a processing device will be described. FIG. 1 is a diagram showing an example of the hardware configuration of a processing device. Each functional unit of the processing device is realized by any combination of hardware and software, centered around a central processing unit (CPU) of any computer, memory, programs loaded into the memory, a storage unit such as a hard disk that stores the programs (which can store programs pre-loaded at the time of shipping the device, as well as programs downloaded from storage media such as CDs (compact discs) or servers on the Internet), and a network connection interface. Those skilled in the art will understand that there are many variations in the implementation methods and devices.

As shown in FIG. 1, the processing device has a processor 1A, memory 2A, input/output interface 3A, peripheral circuit 4A, and bus 5A. The peripheral circuit 4A includes various modules. The processing device does not have to have the peripheral circuit 4A. Note that the processing device may be composed of multiple physically and/or logically separated devices, or may be composed of a single device that is physically and logically integrated. When composed of multiple physically and/or logically separated devices, each of the multiple devices can have the above hardware configuration.

The bus 5A is a data transmission path through which the processor 1A, memory 2A, peripheral circuit 4A, and input/output interface 3A send and receive data to and from each other. The processor 1A is a processing unit such as a CPU or GPU (Graphics Processing Unit). The memory 2A is memory such as RAM (Random Access Memory) or ROM (Read Only Memory). The input/output interface 3A includes interfaces for acquiring information from input devices, external devices, external servers, external sensors, etc., and interfaces for outputting information to output devices, external devices, external servers, etc. Examples of input devices include a keyboard, mouse, and microphone. Examples of output devices include a display, speaker, printer, and mailer. The processor 1A can issue commands to each module and perform calculations based on the results of those calculations.

"Function Configuration"
Next, an example of the functional configuration of the processing device will be described. An example of a functional block diagram of the processing device 10 is shown in FIG. 2. As shown in the figure, the processing device 10 has a grouping unit 11.

The grouping unit 11 has the function of grouping multiple reference targets.

A "reference object" is data for one company for one fiscal year. For example, the 2020 data of ○○○ Co., Ltd. is one reference object, the 2019 data of ○○○ Co., Ltd. is another reference object, and the 2020 data of XXX Co., Ltd. is yet another reference object.

Figure 3 shows a schematic example of information processed by the grouping unit 11. The reference target information shown includes information on multiple reference targets. The information on each reference target includes reference target identification information, company name, fiscal year, and data.

"Reference object identification information" is information that identifies multiple reference objects from each other.
"Company name" is the name of the company that corresponds to each reference object.
"Fiscal year" is the fiscal year that each reference subject corresponds to.
"Data" refers to the data of each referent. As shown, the data of each referent includes financial indicators, technical indicators, and expert indicators.

"Financial indicators" are indicators that show the financial condition of each company for each fiscal year (target period). The financial indicators of the reference object identified by the reference object identification information "M000001" in Figure 3 are the financial indicators for XXX Co., Ltd. for fiscal year 2020. Financial indicators can include any widely used indicator. For example, financial indicators can include at least one of the following: operating profit margin, return on equity, gross profit margin, operating profit margin, selling and general administrative expense ratio, operating profit margin on total capital, return on total capital, total capital turnover, current ratio, equity ratio, quick ratio, debt ratio, fixed asset ratio, fixed asset long-term ratio, operating cash flow, investing cash flow, financing cash flow, labor productivity, capital productivity, labor distribution rate, added value ratio on sales, tangible fixed asset turnover, operating profit growth rate, total capital growth rate, sales growth rate, equity growth rate, research and development expense ratio on sales, and employee growth rate.

"Technical indicators" relate to changes over time in financial indicators for each company for each fiscal year (target period) and prior years. The technical indicators of the reference object identified by the reference object identification information "M000001" in Figure 3 relate to changes over time in financial indicators for XXX Co., Ltd. for fiscal year 2020 and prior years. While the number of years of data referenced by technical indicators varies, it is preferable that technical indicators be data relating to changes over time in financial indicators for four or more years, including each fiscal year and prior years. This enables unprecedented corporate evaluation.

Technical indicators include, for example, at least one of trend indicators and oscillator indicators.

Trend indicators are indicators that show the trend of stock prices and can include any widely used indicator. For example, trend indicators can include at least one of the following: simple moving average, exponential moving average, Ichimoku Kinko Hyo, Bollinger Bands, Zigzag chart, linear regression trend, HL Bands, Envelopes, Keltner Channel, Chaos Alligator, Yin Yang, New Price, Kagi, Balance of Power, Aroon, Heiken Ashi, and Point & Figure.

Oscillator indicators are indicators that show whether a stock is overbought or oversold, and can include any widely used indicator. For example, oscillator indicators can include at least one of the following: stochastics, moving average convergence divergence (MACD), relative strength index (RSI), momentum, directional movement index, divergence rate, divergence price/average, Tom DeMarks range expansion index, average directional index, historical volatility, Williams %R, psychological line, Coppock index, rank correlation index, rate of change, moving average oscillator, ultimate oscillator, Aroon UP/DOWN, Aroon oscillator, money flow index, commodity channel index, volume ratio, strength/weakness ratio, performance, and reverse watch curve.

"Expert indicators" are indicators that are not included in the financial indicators and technical indicators described above, and are generated by processing the financial indicators for each company for each fiscal year (target period) according to predetermined rules. The expert indicator for the reference object identified by the reference object identification information "M000001" in Figure 3 is an indicator generated by processing the financial indicators for fiscal year 2020 of XXX Co., Ltd. according to predetermined rules. The indicator may be a widely known indicator or a newly created indicator. Indicators independently created and used by corporate valuation experts may also be used as expert indicators. For example, expert indicators may include at least one of the following: interest coverage ratio, imbalance between sales and accounts receivable (whether the ratio of the rate of change in accounts receivable to the rate of change in sales has increased for two consecutive periods), and interest expense coefficient (whether the interest expense itself has been borrowed at a high interest rate for a predetermined period).

The grouping unit 11 uses clustering (machine learning) techniques to group multiple reference targets based on the similarities between the financial indicators, technical indicators, and expert indicators described above. The grouping unit 11 may also perform grouping using an ensemble learning technique. That is, the grouping unit 11 may perform grouping using each of multiple types of models and adopt the result of a majority vote of the grouping results using the multiple types of models. Clustering and ensemble learning are widely known techniques, so a detailed description of them will be omitted here.

Through the grouping process performed by the grouping unit 11, multiple reference objects are grouped as shown in Figure 4. Each point in the figure corresponds to one reference object.

Furthermore, through the grouping process performed by the grouping unit 11, group information for each of the multiple groups as shown in FIG. 5 is created and stored in the storage device of the processing device 10. The group information indicates the membership conditions, which are the conditions for belonging to each group, and the members who belong to each group. The membership conditions are expressed using financial indicators, technical indicators, and expert indicators. Both the membership conditions and the members are information obtained as a result of the clustering described above.

"Action and effect"
The processing device 10 of this embodiment groups company data based on the above-mentioned financial indicators, technical indicators, and expert indicators. By grouping company data based on these multiple characteristic indicators, it is possible to obtain desired grouping results. Then, by evaluating companies based on the grouping results, it becomes possible to evaluate companies using a method that has not been used before.

In addition, the processing device 10 of this embodiment can process the data of multiple companies for multiple years as a single reference object and perform grouping. In other words, the processing device 10 does not treat the data of one company as a single reference object and group it, but rather divides the data of one company by year and treats it as multiple reference objects and performs grouping. Then, by performing company evaluation based on the grouping results, it becomes possible to perform company evaluation using a method that has not been used before.

In addition, the processing device 10 of this embodiment can perform grouping using technical indicators related to changes in financial indicators over time for the target fiscal year and a total of four or more years prior to that. By using technical indicators related to such a longer period than conventional methods, corporate evaluation can be achieved using an unprecedented method.

Second Embodiment
The processing device 10 of this embodiment has a function of outputting information that serves as material for evaluating the evaluation target, using the grouping results described in the first embodiment. This will be described in detail below.

Figure 6 shows an example of a functional block diagram of the processing device 10 of this embodiment. As shown in the figure, the processing device 10 has a grouping unit 11, a group identification unit 12, and an information output unit 13.

The group identification unit 12 identifies the group to which the evaluation target belongs from among the groups created by the grouping unit 11.

The "evaluation subject" is data for one company for one fiscal year. For example, the data for fiscal year 2021 for XXX Co., Ltd. is one evaluation subject.

The group identification unit 12 identifies the group to which the evaluation target belongs based on the financial indicators for the evaluation target period (target fiscal year), technical indicators relating to changes over time in the financial indicators for the evaluation target period and prior to that period, and expert indicators generated by processing the financial indicators for the evaluation target period according to predetermined rules. For example, the group identification unit 12 may identify the group to which the evaluation target belongs (the group to which the evaluation target satisfies the membership conditions) by determining whether the evaluation target satisfies the membership conditions for each group (see Figure 5).

The information output unit 13 outputs information about the evaluation object, i.e., information that serves as material for evaluating the evaluation object. The information output unit 13 may output information via an output device such as a display, projection device, printer, or mailer, or may send the information to an external device.

The information output unit 13 outputs information about the group identified by the group identification unit 12 (the group to which the evaluation target belongs) as information about the evaluation target.

For example, the information output unit 13 may output information indicating reference objects belonging to the identified group. Reference objects belonging to the identified group are objects whose financial indicators, technical indicators, and expert indicators have been determined to be similar to those of the evaluation object. Presenting such reference objects means presenting reference objects whose financial indicators, technical indicators, and expert indicators have been similar to those of the evaluation object in the past. For example, a user can predict the future of the evaluation object by referring to the state of the presented reference objects from the fiscal year onwards (the state of financial indicators, technical indicators, and expert indicators), measures taken by those companies from the fiscal year onwards and the results of those measures, etc., and evaluate the evaluation object based on the results of the prediction.

In addition, the information output unit 13 may output information that displays multiple reference targets belonging to the identified group in a ranking format. Figure 7 shows a schematic example of such information. The information shown displays multiple reference targets belonging to the group to which the evaluation target (2021 data for XXX Co., Ltd.) belongs, sorted in order of similarity to the evaluation target.

In addition, the information output unit 13 may create and output information indicating the trend of the data for the target group from the fiscal year onwards, based on data for the target group of multiple reference targets from the fiscal year onwards. The data for which the trend is calculated may be financial indicators, technical indicators, expert indicators, or other data such as sales and profits. For example, the information output unit 13 may calculate the average of the data for the target group of multiple reference targets from the fiscal year onwards as data indicating the trend of the identified group.

In addition, the information output unit 13 may output the membership conditions for belonging to the identified group described above.

In addition, the information output unit 13 may predict future trends in the data to be evaluated based on the data to be evaluated and information indicating trends in the data for the specified group from the fiscal year onwards, and output the prediction results. The data to be predicted may be financial indicators, technical indicators, expert indicators, or other data such as sales and profits.

Figure 7 shows a schematic example of this information. The information shown shows the sales trends for the evaluation target (data for XXX Co., Ltd. for fiscal year 2021). Actual values are from fiscal year 2015 to fiscal year 2021, and forecast values are from fiscal year 2022 to fiscal year 2024. Starting with the actual values for fiscal year 2021, forecast values are shown assuming values change according to the trend in data after the target period for the identified group described above.

Next, an example of the processing flow of the processing device 10 will be explained using the flowchart in Figure 9.

First, the processing device 10 acquires data on the evaluation target (financial indicators, technical indicators, and expert indicators) (S10). Next, the processing device 10 identifies the group to which the evaluation target belongs based on the financial indicators, technical indicators, and expert indicators (S11). The processing device 10 then outputs information on the evaluation target, i.e., information on the group (to which the evaluation target belongs) identified in S11, as information on the evaluation target, i.e., information that will serve as material for evaluating the evaluation target (S12).

The other configurations of the processing device 10 in this embodiment are the same as those in the first embodiment.

The processing device 10 of this embodiment achieves the same effects as the first embodiment. Furthermore, the processing device 10 of this embodiment can output information that serves as material for evaluating the evaluation target, specifically information about a reference target that is in a similar state to the evaluation target. Based on this information, users can evaluate companies using unprecedented methods.

"Variations"
Here, a modified example that can be applied to the first and second embodiments will be described. In the above-described embodiment, data for one year from one company was used as one reference object and one evaluation object. In other words, one year was the target period. As a modified example, the target period may be a quarter or a half year. In other words, data for one quarter from one company may be used as one reference object and one evaluation object, or data for one half year from one company may be used as one reference object and one evaluation object. In the modified example, the same effects as those of the above-described embodiment are achieved.

The above describes embodiments of the present invention with reference to the drawings, but these are merely examples of the present invention, and various other configurations may be adopted. The configurations of the above-described embodiments may be combined with each other, or some of the configurations may be replaced with other configurations. Furthermore, the configurations of the above-described embodiments may be modified in various ways without departing from the spirit of the invention. Furthermore, the configurations and processes disclosed in the above-described embodiments and variations may be combined with each other.

In this specification, "acquisition" includes at least one of the following: "the device retrieves data stored on another device or storage medium (active acquisition)" based on user input or program instructions, such as receiving data by making a request or inquiry to another device, or accessing and reading another device or storage medium; "the device inputs data output from another device (passive acquisition)" based on user input or program instructions, such as receiving data that is distributed (or transmitted, push notification, etc.), or selecting and acquiring data from received data or information; and "the creation of new data by editing data (converting data to text, rearranging data, extracting partial data, changing file format, etc.), and then acquiring that new data."

Some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.
1. A processing device having a grouping means for grouping a plurality of reference targets based on financial indicators for a target period, technical indicators relating to changes in the financial indicators for the target period and prior to that period over time, and expert indicators generated by processing the financial indicators for the target period according to predetermined rules.
2. The processing device according to 1, wherein the grouping means performs the grouping by processing data of each of a plurality of companies in each of a plurality of target periods as one of the reference targets.
3. The processing device according to 1 or 2, wherein the technical indicators include at least one of a trend indicator and an oscillator indicator.
4. The processing device according to any one of 1 to 3, wherein the grouping means performs the grouping using an ensemble learning technique.
5. The processing device according to any one of 1 to 4, wherein the technical indicators relate to changes over time in financial indicators for the target period and for a total of four or more years prior to the target period.
6. Group identification means for identifying a group to which the evaluation target belongs during the evaluation period, based on financial indicators during the evaluation period of the evaluation target, the technical indicators relating to changes in the financial indicators over time during the evaluation period and before, and the expert indicators generated by processing the financial indicators during the evaluation period according to the predetermined rules;
an information output means for outputting information about the specified group as information about the evaluation target;
6. The processing device according to any one of 1 to 5, comprising:
7. The processing device according to 6, wherein the information output means outputs information indicating a trend of financial indicators of the evaluation target after the evaluation period, which is predicted based on the trend of financial indicators of the reference target belonging to the specified group after the evaluation period.
8. The processing device according to 6 or 7, wherein the information output means outputs information indicating the reference object that belongs to the specified group.
9. The processing device according to 8, wherein the information output means outputs information that displays the plurality of reference targets that belong to the specified group in a ranking format.
10. The processing device according to any one of 6 to 9, wherein the information output means outputs the conditions belonging to the specified group expressed using financial indicators, the technical indicators, and the expert indicators.
11. The computer
A processing method that executes a grouping step of grouping multiple reference targets based on financial indicators for a target period, technical indicators relating to changes in the financial indicators for the target period and prior to that period over time, and expert indicators generated by processing the financial indicators for the target period according to predetermined rules.
12. Computer,
A program that functions as a grouping means for grouping multiple reference targets based on financial indicators for a target period, technical indicators relating to changes in the financial indicators for the target period and prior to that period over time, and expert indicators generated by processing the financial indicators for the target period according to predetermined rules.

10 Processing device 11 Grouping unit 12 Group identification unit 13 Information output unit 1A Processor 2A Memory 3A Input/output I/F
4A Peripheral circuit 5A Bus

Claims (10)

A processing device comprising: a memory; and a processor coupled to the memory,
The processor executes the program stored in the memory,
A data acquisition means for acquiring data of a plurality of reference targets; and
a grouping means for grouping the plurality of reference objects based on the data acquired by the data acquisition means ;
It functions as
The data acquisition means
Obtaining financial indicators for a target period of a company to be evaluated, technical indicators calculated from time-series data of financial indicators for the target period and before, and expert indicators calculated from the financial indicators for the target period;
The technical indicators include at least one selected from a simple moving average, an exponential moving average, Ichimoku Kinko Hyo, Bollinger Bands, a Zigzag chart, a linear regression trend, HL Bands, an envelope, a Keltner channel, a Chaos Alligator, a Yin Yang bar, a new price bar, a Kagi bar, a balance of power, an Aroon, a Heikin Ashi, a point and figure, a Stochastics, a Moving Average Convergence/Divergence (MACD), a relative strength index (RSI), momentum, a directional movement index, a divergence rate, a divergence price/average, a Tom DeMarks Range Expansion Index, an average directional index, a historical volatility, a William's %R, a psychological line, a Coppock index, a rank correlation index, a rate of change, a moving average oscillator, an ultimate oscillator, an Aroon UP/DOWN, an Aroon oscillator, a money flow index, a commodity channel index, a volume ratio, a strength/weakness ratio, performance, and a reverse watch curve;
the expert indicators include at least one of an interest coverage ratio, a sales to accounts receivable imbalance, and an interest expense coefficient;
The grouping means
clustering the plurality of reference objects into groups using a clustering model trained to cluster data based on the financial indicators, the technical indicators, and the expert indicators;
A processing device in which the multiple reference objects include a first reference object composed of data for a first target period of a first company, and a second reference object composed of data for a second target period of the first company that is different from the first target period . The processing device according to claim 1 , wherein each of the plurality of reference objects corresponds to financial data for a specific company for a specific period . The processing device according to claim 1 or 2 , wherein the technical indicators are calculated from time-series data of financial indicators for the target period and for a total of four or more years prior to the target period. The processing device described in any one of claims 1 to 3, wherein the processor, by executing the program stored in the memory, further functions as an information output means for outputting information including identification information of the group to which the evaluation target belongs , conditions for belonging to the group, and a list of reference targets belonging to the group . The processing device according to claim 4 , wherein the information output means outputs an average of financial indicators of the reference objects that belong to a group to which the evaluation object belongs, from the target period onward. the information output means outputs information indicating the reference object belonging to a group to which the evaluation object belongs ;
The processing device according to claim 4 , wherein the information indicating the reference object includes a company name and a period corresponding to the reference object . The processing device according to claim 6 , wherein the information output means outputs information in which the plurality of reference objects belonging to the group to which the evaluation object belongs are displayed in a ranking format. 8. The processing device according to claim 4 , wherein the information output means outputs a condition that the evaluation target belongs to a group defined using the financial index, the technical index, and the expert index. a processing device comprising a memory and a processor coupled to the memory,
a data acquisition step of acquiring data of a plurality of reference targets;
a grouping step of grouping the plurality of reference objects based on the data acquired in the data acquisition step;
Run
In the data acquisition step,
Obtaining financial indicators for a target period of a company to be evaluated, technical indicators calculated from time-series data of financial indicators for the target period and before, and expert indicators calculated from the financial indicators for the target period;
The technical indicators include at least one selected from a simple moving average, an exponential moving average, Ichimoku Kinko Hyo, Bollinger Bands, a Zigzag chart, a linear regression trend, HL Bands, an envelope, a Keltner channel, a Chaos Alligator, a Yin Yang bar, a new price bar, a Kagi bar, a balance of power, an Aroon, a Heikin Ashi, a point and figure, a Stochastics, a Moving Average Convergence/Divergence (MACD), a relative strength index (RSI), momentum, a directional movement index, a divergence rate, a divergence price/average, a Tom DeMarks Range Expansion Index, an average directional index, a historical volatility, a William's %R, a psychological line, a Coppock index, a rank correlation index, a rate of change, a moving average oscillator, an ultimate oscillator, an Aroon UP/DOWN, an Aroon oscillator, a money flow index, a commodity channel index, a volume ratio, a strength/weakness ratio, performance, and a reverse watch curve;
the expert indicators include at least one of an interest coverage ratio, a sales to accounts receivable imbalance, and an interest expense coefficient;
In the grouping step,
clustering the plurality of reference objects into groups using a clustering model trained to cluster data based on the financial indicators, the technical indicators, and the expert indicators;
A processing method in which the multiple reference objects include a first reference object composed of data for a first target period of a first company, and a second reference object composed of data for a second target period of the first company that is different from the first target period. A processing device comprising a memory and a processor connected to the memory,
A data acquisition means for acquiring data of a plurality of reference targets; and
a grouping means for grouping the plurality of reference objects based on the data acquired by the data acquisition means;
and make it work,
The data acquisition means
Obtaining financial indicators for a target period of a company to be evaluated, technical indicators calculated from time-series data of financial indicators for the target period and before, and expert indicators calculated from the financial indicators for the target period;
The technical indicators include at least one selected from a simple moving average, an exponential moving average, Ichimoku Kinko Hyo, Bollinger Bands, a Zigzag chart, a linear regression trend, HL Bands, an envelope, a Keltner channel, a Chaos Alligator, a Yin Yang bar, a new price bar, a Kagi bar, a balance of power, an Aroon, a Heikin Ashi, a point and figure, a Stochastics, a Moving Average Convergence/Divergence (MACD), a relative strength index (RSI), momentum, a directional movement index, a divergence rate, a divergence price/average, a Tom DeMarks Range Expansion Index, an average directional index, a historical volatility, a William's %R, a psychological line, a Coppock index, a rank correlation index, a rate of change, a moving average oscillator, an ultimate oscillator, an Aroon UP/DOWN, an Aroon oscillator, a money flow index, a commodity channel index, a volume ratio, a strength/weakness ratio, performance, and a reverse watch curve;
the expert indicators include at least one of an interest coverage ratio, a sales to accounts receivable imbalance, and an interest expense coefficient;
The grouping means
clustering the plurality of reference objects into groups using a clustering model trained to cluster data based on the financial indicators, the technical indicators, and the expert indicators;
A program in which the multiple reference objects include a first reference object composed of data for a first target period of a first company, and a second reference object composed of data for a second target period of the first company that is different from the first target period.